Unverified50% confidenceFactExact time
In its official article on Contextual Retrieval, Anthropic gives the example that an embedding model may find generic content about an error code yet miss an exact "TS-999" match.
1
Sources
50%
Confidence
Long-term
Relevance
10/19/2026
First Seen
Sources
Related Entities
Related Claims
UnverifiedWhen the retrieval context does not contain the answer, many language models fill the gap with plausible-sounding content, which is exactly the hallucination users notice; fixes include instructing the model to answer only from the provided context, giving it a clear way to opt out, requiring a citation for every claim, setting a retrieval score threshold, and logging rejected questions.68% similarUnverifiedThe Contextual Retrieval approach proposed by Anthropic in its technical blog can reduce retrieval failure rates by approximately 49%.65% similarUnverifiedThe paper's diagnostic analysis finds that coding agents often fail not because of missing information, but because the relevant information is already in the context and the model does not act on it.64% similarUnverifiedThe newly added capability declaration fields may affect downstream code that strictly validates the model profile structure64% similarUnverifiedThe five failure modes of retrieval include: vocabulary mismatch, lost context, the question is not the answer, the answer is the entire document, and retrieved but still wrong.63% similar
Cite This Claim
Stable URI
https://kongchang.com/claim/1065176API
curl https://kongchang.com/api/v1/knowledge/claims/1065176MCP
get_claim(id=1065176)